Triple
T14360599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankland Range |
E356087
|
entity |
| Predicate | hasHighestPoint |
P210
|
FINISHED |
| Object |
Frankland Peak
Frankland Peak is the tallest mountain in Tasmania’s remote Frankland Range, known for its rugged terrain and wilderness scenery.
|
E1357245
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Frankland Peak | Statement: [Frankland Range, hasHighestPoint, Frankland Peak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frankland Peak Context triple: [Frankland Range, hasHighestPoint, Frankland Peak]
-
A.
Duffer Peak
Duffer Peak is a mountain summit in Nevada that serves as the highest point of the Pine Forest Range.
-
B.
Ruen Peak
Ruen Peak is the highest summit of the Osogovo mountain range, located on the border between Bulgaria and North Macedonia.
-
C.
Carruthers Peak
Carruthers Peak is a prominent mountain in the Snowy Mountains of New South Wales, Australia, known for its alpine landscapes and proximity to Mount Kosciuszko.
-
D.
Rees Peak
Rees Peak is one of the summits on Arizona’s San Francisco Mountain, part of the volcanic San Francisco Peaks range near Flagstaff.
-
E.
Cradock Peak
Cradock Peak is a prominent mountain summit in South Africa’s Western Cape, known for its challenging hiking routes and panoramic views over the Outeniqua range and surrounding landscapes.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Frankland Peak Triple: [Frankland Range, hasHighestPoint, Frankland Peak]
Generated description
Frankland Peak is the tallest mountain in Tasmania’s remote Frankland Range, known for its rugged terrain and wilderness scenery.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Frankland Peak Target entity description: Frankland Peak is the tallest mountain in Tasmania’s remote Frankland Range, known for its rugged terrain and wilderness scenery.
-
A.
Duffer Peak
Duffer Peak is a mountain summit in Nevada that serves as the highest point of the Pine Forest Range.
-
B.
Ruen Peak
Ruen Peak is the highest summit of the Osogovo mountain range, located on the border between Bulgaria and North Macedonia.
-
C.
Carruthers Peak
Carruthers Peak is a prominent mountain in the Snowy Mountains of New South Wales, Australia, known for its alpine landscapes and proximity to Mount Kosciuszko.
-
D.
Rees Peak
Rees Peak is one of the summits on Arizona’s San Francisco Mountain, part of the volcanic San Francisco Peaks range near Flagstaff.
-
E.
Cradock Peak
Cradock Peak is a prominent mountain summit in South Africa’s Western Cape, known for its challenging hiking routes and panoramic views over the Outeniqua range and surrounding landscapes.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8f54bfb08190a27c0d12731acec2 |
completed | April 14, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05d32f1ee88190b0a215dc78024d62 |
completed | May 14, 2026, 1:50 p.m. |
| NEDg | Description generation | batch_6a05d56219508190baead365509166a3 |
completed | May 14, 2026, 2 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05d6537b9c8190918a56b74c675f7e |
completed | May 14, 2026, 2:04 p.m. |
Created at: April 10, 2026, 1:15 a.m.